Learn ยท Module 06
Transformers
Attention, the full architecture, and how the next token is chosen.
- 1Attention, step by stepFree
- 2Inside a transformer blockFree
- 3Choosing the next token๐ Pro
- 4The context window and the KV cache๐ Pro
- 5Why models hallucinate๐ Pro
- 6Images, audio and other inputs๐ Pro
Build it: projects that use this module